{"id":"W2950484198","doi":"10.1109/fpt.2018.00082","title":"LeFlow: Automatic Compilation of TensorFlow Machine Learning Applications to FPGAs","year":2018,"lang":"en","type":"article","venue":"","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Verilog; Field-programmable gate array; Python (programming language); Computer architecture; Register-transfer level; Compiler; Software; Hardware description language; Computation; Artificial intelligence; Programming language; Machine translation; Code generation; Embedded system; Computer engineering; Logic synthesis; Algorithm; Logic gate; Operating system; Key (lock)","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001220681,0.001500156,0.0005032521,0.0008421045,0.0004542024,0.001122366,0.001505649,0.0005422447,0.01623005],"category_scores_gemma":[0.004657861,0.0007997394,0.0009734974,0.0005212402,0.0007516218,0.001730468,0.001187197,0.001271747,0.003252674],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001077056,"about_ca_system_score_gemma":0.001795115,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002429431,"about_ca_topic_score_gemma":0.003001432,"domain_scores_codex":[0.9993394,0.0001381482,0.00007330381,0.0001397249,0.0002122598,0.00009716255],"domain_scores_gemma":[0.9979262,0.0009019393,0.000155952,0.0005408352,0.0003995229,0.00007556009],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001060915,0.0003958606,0.005072219,0.001533047,0.0002169024,0.001129519,0.0007618391,0.35761,0.0715138,0.07102063,0.07999006,0.4096951],"study_design_scores_gemma":[0.0001378342,0.0001434399,0.0004311123,0.0000831404,0.0000289191,0.0002275176,0.00004100563,0.8852548,0.06000013,0.02023876,0.03336024,0.00005310137],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01969988,0.0001905924,0.8301502,0.0002168788,0.0001896474,0.0002419809,0.0009666664,0.1397015,0.008642634],"genre_scores_gemma":[0.3247247,0.0004128955,0.64187,0.0003774568,0.0001005525,0.0006378723,0.004440128,0.01790033,0.009536047],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01623005,"threshold_uncertainty_score":0.05429494,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01847001742614825,"score_gpt":0.2823632741166452,"score_spread":0.263893256690497,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}